The role of visualisations in social media monitoring systems

Martin Sykora, Thomas W. Jackson, Alexander Von Lunen, Suzanne Elayan, Ann O'Brien

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Social-Media streams are constantly supplying vast volumes of real-time User Generated Content through platforms such as Twitter, Facebook, and Instagram, which makes it a challenge to monitor and understand. Understanding social conversations has now become a major interest for businesses, PR and advertising agencies, as well as law enforcement and government bodies. Monitoring of social-media allows us to observe large numbers of spontaneous, real-time interactions and varied expression of opinion, often fleeting and private. However, human, expert monitoring is generally unfeasible due to the high volumes of data. This has been a major reason for recent research and development work looking at automated social-media monitoring systems. Such systems often keep the human "out of the loop" as an NLP (Natural Language Processing) pipeline and other data-mining algorithms deal with analysing and extracting features and meaning from the data. This is plagued by a variety of problems, mostly due to the heterogenic, inconsistent and context-poor nature of social-media data, where as a result the accuracy and efficacy of such systems suffers. Nevertheless, automated social-media monitoring systems provide for a scalable, streamlined and often efficient way of dealing with big-data streams. The integration of processing outputs from automated systems and feedback to human experts is a challenge and deserves to be addressed in research literature. This paper will establish the role of the human in the social-media monitoring loop, based on prior systems work in this area. The focus of our investigation will be on use of visualisations for effective feedback to human experts. A specific, custom built system's case-study in a social-media monitoring scenario will be considered and suggestions on how to bring back the human "into the loop" will be provided. Also some related ethical questions will be briefly considered. It is hoped that this work will inform and provide valuable insight to help improve development of automated social-media monitoring systems.
LanguageEnglish
Title of host publicationProceedings of the 2nd European Conference on Social Media
EditorsAnabela Mesquita, Paula Peres
Place of PublicationReading, UK
PublisherAcademic Conferences and Publishing International Ltd.
Pages437-444
Number of pages8
ISBN (Electronic)9781910810323
ISBN (Print)9781910810316
Publication statusPublished - 2015
Event2nd European Conference on Social Media - Polytechnic Institute of Porto, Porto, Portugal
Duration: 9 Jul 201510 Jul 2015
Conference number: 2

Conference

Conference2nd European Conference on Social Media
Abbreviated titleECSM 2015
CountryPortugal
CityPorto
Period9/07/1510/07/15

Fingerprint

Visualization
Monitoring
Feedback
Law enforcement
Processing
Data mining
Marketing
Pipelines
Industry

Cite this

Sykora, M., Jackson, T. W., Von Lunen, A., Elayan, S., & O'Brien, A. (2015). The role of visualisations in social media monitoring systems. In A. Mesquita, & P. Peres (Eds.), Proceedings of the 2nd European Conference on Social Media (pp. 437-444). Reading, UK: Academic Conferences and Publishing International Ltd..
Sykora, Martin ; Jackson, Thomas W. ; Von Lunen, Alexander ; Elayan, Suzanne ; O'Brien, Ann. / The role of visualisations in social media monitoring systems. Proceedings of the 2nd European Conference on Social Media. editor / Anabela Mesquita ; Paula Peres. Reading, UK : Academic Conferences and Publishing International Ltd., 2015. pp. 437-444
@inproceedings{e86003e8651f4145b7052abf8f368141,
title = "The role of visualisations in social media monitoring systems",
abstract = "Social-Media streams are constantly supplying vast volumes of real-time User Generated Content through platforms such as Twitter, Facebook, and Instagram, which makes it a challenge to monitor and understand. Understanding social conversations has now become a major interest for businesses, PR and advertising agencies, as well as law enforcement and government bodies. Monitoring of social-media allows us to observe large numbers of spontaneous, real-time interactions and varied expression of opinion, often fleeting and private. However, human, expert monitoring is generally unfeasible due to the high volumes of data. This has been a major reason for recent research and development work looking at automated social-media monitoring systems. Such systems often keep the human {"}out of the loop{"} as an NLP (Natural Language Processing) pipeline and other data-mining algorithms deal with analysing and extracting features and meaning from the data. This is plagued by a variety of problems, mostly due to the heterogenic, inconsistent and context-poor nature of social-media data, where as a result the accuracy and efficacy of such systems suffers. Nevertheless, automated social-media monitoring systems provide for a scalable, streamlined and often efficient way of dealing with big-data streams. The integration of processing outputs from automated systems and feedback to human experts is a challenge and deserves to be addressed in research literature. This paper will establish the role of the human in the social-media monitoring loop, based on prior systems work in this area. The focus of our investigation will be on use of visualisations for effective feedback to human experts. A specific, custom built system's case-study in a social-media monitoring scenario will be considered and suggestions on how to bring back the human {"}into the loop{"} will be provided. Also some related ethical questions will be briefly considered. It is hoped that this work will inform and provide valuable insight to help improve development of automated social-media monitoring systems.",
keywords = "social-media monitoring, visualisations, user interface design, decision support systems, Twitter",
author = "Martin Sykora and Jackson, {Thomas W.} and {Von Lunen}, Alexander and Suzanne Elayan and Ann O'Brien",
year = "2015",
language = "English",
isbn = "9781910810316",
pages = "437--444",
editor = "Anabela Mesquita and Paula Peres",
booktitle = "Proceedings of the 2nd European Conference on Social Media",
publisher = "Academic Conferences and Publishing International Ltd.",

}

Sykora, M, Jackson, TW, Von Lunen, A, Elayan, S & O'Brien, A 2015, The role of visualisations in social media monitoring systems. in A Mesquita & P Peres (eds), Proceedings of the 2nd European Conference on Social Media. Academic Conferences and Publishing International Ltd., Reading, UK, pp. 437-444, 2nd European Conference on Social Media, Porto, Portugal, 9/07/15.

The role of visualisations in social media monitoring systems. / Sykora, Martin; Jackson, Thomas W.; Von Lunen, Alexander; Elayan, Suzanne; O'Brien, Ann.

Proceedings of the 2nd European Conference on Social Media. ed. / Anabela Mesquita; Paula Peres. Reading, UK : Academic Conferences and Publishing International Ltd., 2015. p. 437-444.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - The role of visualisations in social media monitoring systems

AU - Sykora, Martin

AU - Jackson, Thomas W.

AU - Von Lunen, Alexander

AU - Elayan, Suzanne

AU - O'Brien, Ann

PY - 2015

Y1 - 2015

N2 - Social-Media streams are constantly supplying vast volumes of real-time User Generated Content through platforms such as Twitter, Facebook, and Instagram, which makes it a challenge to monitor and understand. Understanding social conversations has now become a major interest for businesses, PR and advertising agencies, as well as law enforcement and government bodies. Monitoring of social-media allows us to observe large numbers of spontaneous, real-time interactions and varied expression of opinion, often fleeting and private. However, human, expert monitoring is generally unfeasible due to the high volumes of data. This has been a major reason for recent research and development work looking at automated social-media monitoring systems. Such systems often keep the human "out of the loop" as an NLP (Natural Language Processing) pipeline and other data-mining algorithms deal with analysing and extracting features and meaning from the data. This is plagued by a variety of problems, mostly due to the heterogenic, inconsistent and context-poor nature of social-media data, where as a result the accuracy and efficacy of such systems suffers. Nevertheless, automated social-media monitoring systems provide for a scalable, streamlined and often efficient way of dealing with big-data streams. The integration of processing outputs from automated systems and feedback to human experts is a challenge and deserves to be addressed in research literature. This paper will establish the role of the human in the social-media monitoring loop, based on prior systems work in this area. The focus of our investigation will be on use of visualisations for effective feedback to human experts. A specific, custom built system's case-study in a social-media monitoring scenario will be considered and suggestions on how to bring back the human "into the loop" will be provided. Also some related ethical questions will be briefly considered. It is hoped that this work will inform and provide valuable insight to help improve development of automated social-media monitoring systems.

AB - Social-Media streams are constantly supplying vast volumes of real-time User Generated Content through platforms such as Twitter, Facebook, and Instagram, which makes it a challenge to monitor and understand. Understanding social conversations has now become a major interest for businesses, PR and advertising agencies, as well as law enforcement and government bodies. Monitoring of social-media allows us to observe large numbers of spontaneous, real-time interactions and varied expression of opinion, often fleeting and private. However, human, expert monitoring is generally unfeasible due to the high volumes of data. This has been a major reason for recent research and development work looking at automated social-media monitoring systems. Such systems often keep the human "out of the loop" as an NLP (Natural Language Processing) pipeline and other data-mining algorithms deal with analysing and extracting features and meaning from the data. This is plagued by a variety of problems, mostly due to the heterogenic, inconsistent and context-poor nature of social-media data, where as a result the accuracy and efficacy of such systems suffers. Nevertheless, automated social-media monitoring systems provide for a scalable, streamlined and often efficient way of dealing with big-data streams. The integration of processing outputs from automated systems and feedback to human experts is a challenge and deserves to be addressed in research literature. This paper will establish the role of the human in the social-media monitoring loop, based on prior systems work in this area. The focus of our investigation will be on use of visualisations for effective feedback to human experts. A specific, custom built system's case-study in a social-media monitoring scenario will be considered and suggestions on how to bring back the human "into the loop" will be provided. Also some related ethical questions will be briefly considered. It is hoped that this work will inform and provide valuable insight to help improve development of automated social-media monitoring systems.

KW - social-media monitoring

KW - visualisations

KW - user interface design

KW - decision support systems

KW - Twitter

UR - http://www.academic-bookshop.com/ourshop/prod_3918422-ECSM-2015-2nd-European-Conference-on-Social-Media-Porto-Portugal-ISBN-9781910810316-ISSN-20557213.html

M3 - Conference contribution

SN - 9781910810316

SP - 437

EP - 444

BT - Proceedings of the 2nd European Conference on Social Media

A2 - Mesquita, Anabela

A2 - Peres, Paula

PB - Academic Conferences and Publishing International Ltd.

CY - Reading, UK

ER -

Sykora M, Jackson TW, Von Lunen A, Elayan S, O'Brien A. The role of visualisations in social media monitoring systems. In Mesquita A, Peres P, editors, Proceedings of the 2nd European Conference on Social Media. Reading, UK: Academic Conferences and Publishing International Ltd. 2015. p. 437-444